Xiaomi MiMo Benchmarks — SWE-Bench 73.4%, AIME 68.2%, Throughput & API Pricing
Last updated: July 15, 2026 · Originally published: December 18, 2025
Xiaomi MiMo performance benchmarks: 73.4% SWE-Bench Verified (V2-Flash), 68.2% AIME 2024 (MiMo-7B-RL), 1M context (V2.5-Pro), 150 tok/s throughput, $1/$3 per M tokens pricing. Frontier-competitive open-weight LLM.
4. Benchmarks and Evaluation
MiMo's benchmark performance varies meaningfully by model tier. We report the most relevant evaluations here, with comparisons to equivalent-weight-class open-weight models and select closed-source references for context.
4.1 SWE-Bench Verified
| Model | SWE-Bench Verified | Params Active | License |
|---|---|---|---|
| MiMo-V2-Flash | 73.4% | 15B MoE | MIT |
| DeepSeek-R1 | 68.3% | 37B dense | MIT |
| Llama 4 Maverick (Meta) | — | Open-weight multimodal | Custom |
| GPT-5.5 | ~88.7% | Unknown | Closed |
| Claude Opus 4.5 | 76.80% | Unknown | Closed |
| Claude Opus 4.8 | ~80.9% | Unknown | Closed |
| DeepSeek-V3 | ~39% | 37B MoE | MIT |
V2-Flash's 73.4% on SWE-Bench is the highest published result among open-weight models. For context, the top closed-source models include GPT-5.3 Codex (85.0%), Claude Opus 4.8 (~80.9%), Claude Opus 4.5 (76.80%), and Gemini 3 Flash (75.80%). This reflects the intense emphasis on code reasoning during MiMo's RL training pipeline.
4.2 AIME 2024 (Mathematics)
| Model | AIME 2024 | Size |
|---|---|---|
| MiMo-7B-RL | 68.2% | 7B |
| DeepSeek-R1-7B | 65.4% | 7B |
| Qwen2.5-Math-7B | 62.0% | 7B |
| Math-Shepherd-7B | 60.1% | 7B |
MiMo-7B-RL leads the 7B class on AIME 2024 by nearly 3 percentage points. Since AIME 2024 measures multi-step mathematical reasoning, this is a strong signal that MiMo's RL methodology produces genuinely better reasoning chains, not just memorized patterns.
4.3 Throughput and Context
Inference speed at 150 tok/s (V2-Flash on A100) places MiMo competitively with other MoE models like DeepSeek-V4 Pro and ahead of dense models in the same parameter class. The 1M context window of V2.5-Pro is among the largest available — comparable to Gemini 2.5 Pro (1M) and GPT-5.5 (1.05M).
4.4 Competitive Pricing at API Level
MiMo API pricing was permanently reduced in May 2026:
| Provider | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| MiMo-V2.5-Pro | $1 | $3 |
| MiMo-V2-Flash | $0.50 | $1.50 |
| GPT-5.5 | $5 | $30 |
| GPT-5.4 | $2 | $12 |
| Claude Opus 4.5 | $15 | $75 |
| Claude Sonnet 4.6 | $3 | $15 |
| DeepSeek-V4 Pro | $0.435 | $0.87 |
| DeepSeek-R1 | $0.55 | $2.19 |
| Gemini 2.5 Pro | $1.25 | $10 |
| Mistral Large 3 | $2 | $6 |
MiMo sits in the middle of the pricing spectrum — more expensive than DeepSeek, but significantly cheaper than GPT-5.5, GPT-5.4, and Claude Opus 4.5. The MIT licensing on weights means self-hosting reduces marginal inference cost to electricity + hardware, making MiMo cost-competitive at any scale for teams with GPU infrastructure.